LoopUS converts pretrained LLMs into looped latent refinement models via block decomposition, selective gating, random deep supervision, and confidence-based early exiting to improve reasoning performance.
Rectified linear units improve restricted boltzmann machines
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
GroupKAN reduces KAN parameter scaling via intra-group spline mappings, delivering 79.80% average IoU (+1.11% over U-KAN) at 47.6% of the parameters on BUSI, GlaS, and CVC datasets.
Multi-pipeline machine learning with conformal prediction up-ranks subthreshold LIGO/Virgo candidates, including GW200311_103121, as signal-like.
citing papers explorer
-
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
LoopUS converts pretrained LLMs into looped latent refinement models via block decomposition, selective gating, random deep supervision, and confidence-based early exiting to improve reasoning performance.
-
GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling
GroupKAN reduces KAN parameter scaling via intra-group spline mappings, delivering 79.80% average IoU (+1.11% over U-KAN) at 47.6% of the parameters on BUSI, GlaS, and CVC datasets.
-
Combining gravitational wave search pipelines to find subthreshold signals in GWTC-5.0
Multi-pipeline machine learning with conformal prediction up-ranks subthreshold LIGO/Virgo candidates, including GW200311_103121, as signal-like.